© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85009
    Prev
    Next
    INDEX
    Explanations

    actions and their consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </td>
    -1.88
    _
    -1.78
    </em>
    -1.76
    𓐍
    -1.62
    攞
    -1.49
     و
    -1.48
     géographie
    -1.45
    ch
    -1.40
     convince
    -1.37
    汌
    -1.37
    POSITIVE LOGITS
     WITH
    1.48
    volvement
    1.47
    neko
    1.41
     visar
    1.38
    rinology
    1.33
    devil
    1.32
     vieler
    1.32
    elang
    1.32
     adiv
    1.32
    yit
    1.31
    Activations Density 0.646%

    No Known Activations